Upload folder using huggingface_hub

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3959ca0c74151ec42369e57834531fa02cf26e6b6e4067b8c4513d0fa6b8d5da
+size 4479527801

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8050ba2cc9a05b218032cb92cdd100d7efb99aa1ecd84e66b393d878de8ff25b
+size 2239787829

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87dea905d87c81844d15d9dc5bf366bc5656f2433e5216b5cde12edbc8651e5f
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e254f74d9e951589443e6ee8c3e69b258c2405bb4b95356230d436af461743
+size 627

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": 0.03876456990838051,
+  "best_model_checkpoint": "../model/xlm-roberta-large_8_5e-06_512_train_danish_5_512/tmp/checkpoint-138971",
+  "epoch": 8.0,
+  "global_step": 158824,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0719,
+      "step": 19853
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8061753891099582,
+      "eval_loss": 0.05261862650513649,
+      "eval_runtime": 485.7414,
+      "eval_samples_per_second": 40.872,
+      "eval_steps_per_second": 5.11,
+      "step": 19853
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0459,
+      "step": 39706
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8427441696469048,
+      "eval_loss": 0.04516961798071861,
+      "eval_runtime": 485.7767,
+      "eval_samples_per_second": 40.869,
+      "eval_steps_per_second": 5.109,
+      "step": 39706
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0354,
+      "step": 59559
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8623885558857604,
+      "eval_loss": 0.041948962956666946,
+      "eval_runtime": 484.5309,
+      "eval_samples_per_second": 40.974,
+      "eval_steps_per_second": 5.122,
+      "step": 59559
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-06,
+      "loss": 0.0277,
+      "step": 79412
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8793129501838514,
+      "eval_loss": 0.04084821045398712,
+      "eval_runtime": 484.6834,
+      "eval_samples_per_second": 40.961,
+      "eval_steps_per_second": 5.121,
+      "step": 79412
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0217,
+      "step": 99265
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8918047650229185,
+      "eval_loss": 0.03935844823718071,
+      "eval_runtime": 485.8351,
+      "eval_samples_per_second": 40.864,
+      "eval_steps_per_second": 5.109,
+      "step": 99265
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0171,
+      "step": 119118
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.899712889739586,
+      "eval_loss": 0.03974699229001999,
+      "eval_runtime": 483.2863,
+      "eval_samples_per_second": 41.079,
+      "eval_steps_per_second": 5.136,
+      "step": 119118
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.5e-06,
+      "loss": 0.0137,
+      "step": 138971
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9080743464463809,
+      "eval_loss": 0.03876456990838051,
+      "eval_runtime": 485.012,
+      "eval_samples_per_second": 40.933,
+      "eval_steps_per_second": 5.117,
+      "step": 138971
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.0106,
+      "step": 158824
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9115498917040246,
+      "eval_loss": 0.03986608609557152,
+      "eval_runtime": 484.9173,
+      "eval_samples_per_second": 40.941,
+      "eval_steps_per_second": 5.118,
+      "step": 158824
+    }
+  ],
+  "max_steps": 198530,
+  "num_train_epochs": 10,
+  "total_flos": 1.1841805507553526e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606474c534d376da2da828e72f44e1ba52fcfae1094677f136f3b2f008267b8e
+size 3643